coll/tuned: Fix MPI_IN_PLACE processing in tuned algorithms #6007
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
PR open-mpi#5450 addresses MPI_IN_PLACE processing for basic collective algorithms. But in conjunction with that, we need to check for MPI_IN_PLACE in tuned paths as well before calling ompi_datatype_type_size() as otherwise we segfault. MPI spec also stipulates to ignore sendcount and sendtype for Alltoall and Allgatherv operations. So, extending the check to these algorithms as well. Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@intel.com> (cherry picked from commit 88d7810)
gpaulsen
approved these changes
Oct 31, 2018
| } | ||
|
|
||
| /* Determine complete data size */ | ||
| ompi_datatype_type_size(sdtype, &dsize); |
There was a problem hiding this comment.
This looks good, I verified that ompi_coll_base_allgatherv_intra_two_procs already has a check for IN_PLACE, so no need to add above that. Looks good.
|
@hppritcha This is a simple, straightfoward bugfix. Wanna pick it up for 4.0.0? It's MPI_IN_PLACE, and I'm not sure how many are using that "feature". |
|
@hppritcha , @gpaulsen - PR #5474 did cherry-pick the fix for MPI_IN_PLACE processing in coll/base/allgather to 4.0.x branch. But I don't see that in 3.0.x or 3.1.x branches. Should PR #5474 along with this one be cherry-picked to v3.0x/v3.1.x? |
|
(bits of) 6bb356a should be also backported to the |
hppritcha
approved these changes
Nov 2, 2018
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR #5450 addresses MPI_IN_PLACE processing for basic collective algorithms.
But in conjunction with that, we need to check for MPI_IN_PLACE in tuned paths
as well before calling ompi_datatype_type_size() as otherwise we segfault.
MPI spec also stipulates to ignore sendcount and sendtype for Alltoall and
Allgatherv operations. So, extending the check to these algorithms as well.
Signed-off-by: Aravind Gopalakrishnan Aravind.Gopalakrishnan@intel.com
(cherry picked from commit 88d7810)